Models / Qwen3.8-27B
Qwen3.8-27B
Qwen3.8-27B is best for agents and tool use; a strong pick at a modest price. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $1.12.
Results 16 Nov 2026 · 55 results · 2 sources
Test Qwen3.8-27B on your prompt → It runs beside the models you could use instead, with every answer checked and costed.
- Price per million tokens
- $0.50 in · $3.00 out
Alibaba's list price, 10 Nov 2026 · compare prices - Speed
- 46 tokens a second; on its test prompt the answer starts after 44.4 s, thinking time included
Artificial Analysis, on its usual API, at low reasoning; 39–46 across 4 settings - Intelligence Index
- 33.7
Artificial Analysis, at xhigh reasoning; 20.2–33.7 across 4 settings - Spring Prompt overall
- Not ranked yet
needs our benchmarks and two groups of results - Developer
- Alibaba, based in China
Weights published - Released
- 14 Aug 2026
1,048,575 tokens of context
Where it stands among the models you could choose
Available models grouped by price, intelligence, speed and developer location, plus models with published weights. Retired models are excluded.
| Among | Intelligence Index | Spring Prompt overall | Price, blended | Speed |
|---|---|---|---|---|
| Models available today | 44th of 185Claude Opus 5.5 | – | $1.12 blended, 58th percentilecheapest: Mistral Nemo | 58th of 65Nemotron 3.5 Super VL |
| Models priced $1–3 per million tokens | 7th of 34Muse Spark 1.3 | – | sets this group | 9th of 9Muse Spark 1.3 |
| Models with similar intelligence | sets this group | – | $1.12 blended, 29th percentilecheapest: DeepSeek-V4-Flash (0731) | 5th of 5Beam 1.0 501B A23B |
| Models writing under 50 tokens a second | 6th of 9MiMo-V2.6-Pro | – | $1.12 blended, 62nd percentilecheapest: Phi-4 | sets this group |
| Models from developers based in China | 14th of 75MiMo-V2.6-Pro | – | $1.12 blended, 76th percentilecheapest: Qwen3.5-9B | 18th of 23DeepSeek-V4.1-Flash |
| Open-weights models | 15th of 104MiMo-V2.6-Pro | – | $1.12 blended, 81st percentilecheapest: Mistral Nemo | 37th of 43Nemotron 3.5 Super VL |
The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.
How good is it, and for what?
Each use case ranks the available models its benchmarks measured, then those priced $1–3 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.
Product listingsTurning a sparse product feed and photos into listings that can go live
- CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is
- DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled
- SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending
- ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls
| Benchmark | Qwen3.8-27B | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported | 5.6% | 47th of 107 | Kimi K3.1 Pro 67.2% |
| Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported | 79.8% | 23rd of 107 | Claude Fable 5.1 91.4% |
| Artificial AnalysisArtificial Analysis: τ-bench banking · reported | 48.0% | 5th of 104 | Grok 4.6 50.7% |
- tau2-bench: pending. Its latest results are dated 26 May 2026, before this model was released.
- Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
- OpenHands Index: pending. Its latest results are dated 30 Jun 2026, before this model was released.
- Microsoft STATE-Bench: pending. Its latest results are dated 29 May 2026, before this model was released.
- Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects
- APEX-Agents: has not measured this model.
- GDP.pdf: has not measured this model.
- Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge
| Benchmark | Qwen3.8-27B | Rank among available | Best available |
|---|---|---|---|
| Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported | 33.7 | 44th of 185 | Claude Opus 5.5 57.6 |
| Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported | 33.9% | 67th of 186 | Claude Opus 5.5 61.4% |
| Artificial AnalysisArtificial Analysis: GPQA Diamond · reported | 90.5% | 34th of 168 | GPT-6 Astra 96.3% |
WritingWhat people prefer in blind comparisons, and judged writing quality
| Benchmark | Qwen3.8-27B | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text: overall · reported | 1,438 | 66th of 153 | Gemini 4 Argon 1,525 |
- UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers
| Benchmark | Qwen3.8-27B | Rank among available | Best available |
|---|---|---|---|
| Arena (formerly LMArena)Arena Text factuality: overall · reported | 1,438 | 65th of 109 | Gemini 4 Argon 1,511 |
- Vectara Hallucination Leaderboard: has not measured this model.
- SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess)
- BulletBench: has not measured this model.
Nearest alternatives
- Cheaper at similar intelligenceMiMo-V2.6-Flash$0.18 blended · Intelligence Index 37.9Compare with Qwen3.8-27B →
Against Qwen3.8-27B at $1.12 blended, Intelligence Index 33.7. "Similar intelligence" means within 4 points or better.
Where to run it
25 hosts on OpenRouter at the standard service tier, with a median of $0.66 blended per million tokens; quantisation where the host states it: FP8, FP4, BF16, FP16. Cheapest first.
| Host | Quantisation | Input | Output | Blended |
|---|---|---|---|---|
| PrimeIntellect | FP8 | $0.05 | $0.38 | $0.13 |
| Chutes | FP8 | $0.04 | $1.25 | $0.34 |
| Near AI | FP8 | $0.04 | $1.35 | $0.37 |
| StreamLake | not stated | $0.17 | $1.05 | $0.39 |
| Darkbloom | FP4 | $0.04 | $1.50 | $0.40 |
| Mancer 2 | FP8 | $0.15 | $1.25 | $0.42 |
| Tenstorrent | FP8 | $0.15 | $1.60 | $0.51 |
| Ionstream | FP8 | $0.04 | $1.95 | $0.52 |
Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026; the 17 dearer hosts are left out.
Against the alternatives
The models you would most likely weigh it against: the leaders of the groups above.
Scroll sideways to see every alternative.
| Qwen3.8-27B | Muse Spark 1.3 most intelligent at $1–3 per million tokens | DeepSeek-V4-Flash (0731) cheapest with similar intelligence | Beam 1.0 501B A23B fastest with similar intelligence | Claude Opus 5.5 most intelligent available today | |
|---|---|---|---|---|---|
| Price per million tokens | $1.12 | $2.00 | $0.20 | $0.60 | $8.00 |
| Tokens a second | 46 | 254 | – | 323 | 96 |
| Intelligence Index | 33.7 | 48.1 | 34.3 | 30.3 | 57.6 |
| Spring Prompt overall | – | 59 | – | – | 82 |
| Rank among available models, by use case | |||||
| Product listings | – | 17th | – | – | 13th |
| Decks from an analysis | – | 25th | – | – | 7th |
| User surveys | – | – | – | – | 4th |
| Marketing planning | – | 25th | – | – | 9th |
| Agents and tool use | 38th of 159 | 13th | 43rd | 75th | 3rd |
| Professional work | – | 8th | – | – | 3rd |
| Reasoning and knowledge | 57th of 187 | 11th | 47th | 63rd | 1st |
| Writing | 70th of 169 | 7th | – | – | 5th |
| Sticking to the facts | 86th of 139 | 11th | 105th | – | 3rd |
| Speed under pressure | – | 33rd | – | – | – |
| Side by side → | Side by side → | ||||
Shaded figures are better than Qwen3.8-27B's. A dash means no result.
Where it has been measured
7th most intelligent of the 34 models priced $1–3 per million tokens. Among models available today, in the top quarter (by percentile) for agents and tool use.
- Arena (formerly LMArena)11 results
- Artificial Analysis44 results
- Berkeley Function Calling Leaderboard (BFCL) V4Pending: latest results 16 Dec 2025
- Microsoft STATE-BenchPending: latest results 1 Jul 2026
- OpenHands IndexPending: latest results 30 Jun 2026
- tau2-benchPending: latest results 3 Aug 2026
- BulletBenchNot measured
- CatalogBenchNot measured
- DeckBenchNot measured
- ROASBenchNot measured
- SurveyBenchNot measured
- APEX-AgentsNot measured
- GDP.pdfNot measured
- Remote Labor IndexNot measured
- SimpleQA Verified (Epoch AI)Not measured
- UGI LeaderboardNot measured
- Vectara Hallucination LeaderboardNot measured
- Vending-Bench 2Not measured
Every result
55 published results from 2 sources, each in the source's own units, with the configuration that produced it.
Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 11 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Arena Agent: confirmed task successIPS effect estimate, higher is better | 0.01 -0.00–0.02 |
29 of 50 | Qwen3.8-27B (arena agent) | 2 Oct 2026 |
| Arena Agent: praise over complaintIPS effect estimate, higher is better | -0.03 -0.05–-0.00 |
33 of 50 | Qwen3.8-27B (arena agent) | 2 Oct 2026 |
| Arena Agent: steerabilityIPS effect estimate, higher is better | -0.00 -0.01–0.00 |
35 of 50 | Qwen3.8-27B (arena agent) | 2 Oct 2026 |
| Arena Agent: tool groundingIPS effect estimate, higher is better | -0.00 -0.00–-0.00 |
40 of 50 | Qwen3.8-27B (arena agent) | 2 Oct 2026 |
| Arena Text factuality: overallArena rating, higher is better | 1,438 1,434–1,443 |
96 of 182 | Qwen3.8-27B | 2 Oct 2026 |
| Arena Text: business, management and financeArena rating, higher is better | 1,436 1,426–1,447 |
107 of 406 | Qwen3.8-27B | 2 Oct 2026 |
| Arena Text: creative writingArena rating, higher is better | 1,364 1,353–1,374 |
163 of 411 | Qwen3.8-27B | 2 Oct 2026 |
| Arena Text: expert promptsArena rating, higher is better | 1,476 1,462–1,489 |
80 of 363 | Qwen3.8-27B | 2 Oct 2026 |
| Arena Text: instruction followingArena rating, higher is better | 1,426 1,418–1,434 |
101 of 413 | Qwen3.8-27B | 2 Oct 2026 |
| Arena Text: overallArena rating, higher is better | 1,438 1,432–1,443 |
99 of 413 | Qwen3.8-27B | 2 Oct 2026 |
| Arena Text: writing, literature and languageArena rating, higher is better | 1,397 1,388–1,407 |
133 of 412 | Qwen3.8-27B | 2 Oct 2026 |
Not shown: Not a success rate: the estimated effect of choosing this model as the agent's orchestrator, against an even mix of the models tested, inside Arena's own harness.
Artificial Analysis · reported by Artificial Analysis · 44 results
| Measure | Value | Rank | Configuration | Dated |
|---|---|---|---|---|
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 58.2 | 80 of 187 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 56.1 | 85 of 187 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 44.6 | 111 of 187 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better | 68.1 | 60 of 187 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 26.2 | 144 of 413 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 27.6 | 132 of 413 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 20.2 | 210 of 413 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better | 33.7 | 97 of 413 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 84.5% | 127 of 360 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 84.5% | 127 of 360 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 81.8% | 161 of 360 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: GPQA Diamond% of questions, higher is better | 90.5% | 60 of 360 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 14.0% | 240 of 419 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 14.1% | 239 of 419 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 12.1% | 255 of 419 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Humanity's Last Exam% of questions, higher is better | 33.9% | 129 of 419 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 77.3% | 128 of 407 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 79.7% | 86 of 407 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 69.3% | 206 of 407 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better | 82.0% | 44 of 407 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 46.4 | 119 of 137 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 43.0 | 125 of 137 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 42.7 | 126 of 137 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Output speedtokens per second, higher is better | 39.2 | 130 of 137 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 40.0% | 163 of 205 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 39.0% | 168 of 205 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 36.2% | 179 of 205 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: SciCode% of problems, higher is better | 46.6% | 139 of 205 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 67.4% | 72 of 188 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 65.2% | 76 of 188 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 49.1% | 110 of 188 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better | 79.8% | 47 of 188 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 2.5% | 120 of 204 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 5.1% | 110 of 204 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 0.0% | 152 of 204 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better | 5.6% | 108 of 204 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 44.4 | 108 of 137 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 47.7 | 113 of 137 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 1.27 | 33 of 137 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: Time to first answer tokenseconds, lower is better | 52.4 | 119 of 137 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 32.2% | 54 of 175 | Qwen3.8-27B (low reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 47.4% | 8 of 175 | Qwen3.8-27B (medium reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 20.0% | 88 of 175 | Qwen3.8-27B (no reasoning) | 20 Oct 2026 |
| Artificial Analysis: τ-bench banking% of tasks, higher is better | 48.0% | 6 of 175 | Qwen3.8-27B (xhigh reasoning) | 20 Oct 2026 |
Not shown: Not your codebase or tools.
Will Qwen3.8-27B work for your product?
Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.
New here? Your email starts a free trial. No credit card needed.